CN115526837A - Abnormal driving detection method and device, electronic equipment and medium - Google Patents

Abnormal driving detection method and device, electronic equipment and medium Download PDF

Info

Publication number
CN115526837A
CN115526837A CN202211059053.1A CN202211059053A CN115526837A CN 115526837 A CN115526837 A CN 115526837A CN 202211059053 A CN202211059053 A CN 202211059053A CN 115526837 A CN115526837 A CN 115526837A
Authority
CN
China
Prior art keywords
image
microwave radar
target
matched
road area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211059053.1A
Other languages
Chinese (zh)
Inventor
顾超
许孝勇
陶征
朱大安
仇世豪
王长冬
张辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Hurys Intelligent Technology Co Ltd
Original Assignee
Nanjing Hurys Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Hurys Intelligent Technology Co Ltd filed Critical Nanjing Hurys Intelligent Technology Co Ltd
Priority to CN202211059053.1A priority Critical patent/CN115526837A/en
Publication of CN115526837A publication Critical patent/CN115526837A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/194Segmentation; Edge detection involving foreground-background segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • G06T7/246Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10032Satellite or aerial image; Remote sensing
    • G06T2207/10044Radar image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20212Image combination
    • G06T2207/20216Image averaging
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30248Vehicle exterior or interior
    • G06T2207/30252Vehicle exterior; Vicinity of vehicle
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30248Vehicle exterior or interior
    • G06T2207/30252Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256Lane; Road marking

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Traffic Control Systems (AREA)

Abstract

The embodiment of the invention discloses a method and a device for detecting abnormal driving, electronic equipment and a medium. Wherein, the method comprises the following steps: acquiring at least two continuous microwave radar images matched with a road area; the gray value of each pixel point in the microwave radar image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area; carrying out background separation on each microwave radar image to obtain a foreground image matched with each microwave radar image; determining at least one target vehicle track according to each foreground image; and judging whether abnormal driving behaviors exist or not according to the target vehicle track and the road area. The technical scheme solves the problems of high cost, low detection efficiency and possible missing detection caused by manual identification by a worker through inquiring the monitoring video, realizes quick and accurate identification of abnormal driving behaviors in a road, and ensures traffic safety.

Description

Abnormal driving detection method and device, electronic equipment and medium
Technical Field
The present invention relates to the field of image detection technologies, and in particular, to a method and an apparatus for detecting abnormal driving, an electronic device, and a medium.
Background
With the improvement of highway infrastructure in China, the number of passing vehicles is continuously increased, and traffic safety becomes an important social problem. At the exit of the ramp of the expressway, traffic violations such as parking, backing or retrograde motion of a driver occur occasionally, and the traffic violations are major potential safety hazards of road traffic.
In the prior art, abnormal driving behaviors such as parking, backing or retrograde motion and the like at an exit of a ramp of an expressway are detected, a monitoring device is usually arranged near the exit of the ramp, and workers perform manual identification by inquiring monitoring videos. How to solve the problem of road traffic safety in the field of digital traffic becomes an increasingly important topic.
Disclosure of Invention
The invention provides an abnormal driving detection method, an abnormal driving detection device, electronic equipment and a medium, which are used for rapidly and accurately identifying abnormal driving behaviors in a road so as to guarantee traffic safety.
According to an aspect of the present invention, there is provided an abnormal driving detection method, the method including:
acquiring at least two continuous microwave radar images matched with a road area;
the gray value of each pixel point in the microwave radar image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area;
background separation is carried out on each microwave radar image to obtain a foreground image matched with each microwave radar image;
determining at least one target vehicle track according to each foreground image;
and judging whether abnormal driving behaviors exist or not according to the target vehicle track and the road area.
According to another aspect of the present invention, there is provided an abnormal driving detection apparatus including:
the image acquisition module is used for acquiring at least two continuous microwave radar images matched with the road area;
the gray value of each pixel point in the microwave radar image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area;
the background separation module is used for carrying out background separation on each microwave radar image to obtain a foreground image matched with each microwave radar image;
the vehicle track determining module is used for determining at least one target vehicle track according to each foreground image;
and the driving behavior judging module is used for judging whether abnormal driving behaviors exist according to the target vehicle track and the road area.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the abnormal driving detection method according to any embodiment of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the abnormal driving detection method according to any one of the embodiments of the present invention when the computer instructions are executed.
According to the technical scheme, background separation is carried out on each microwave radar image through at least two continuous microwave radar images matched with the road area to obtain the foreground image matched with each microwave radar image, at least one target vehicle track is determined according to each foreground image, whether abnormal driving behaviors exist or not is judged according to the target vehicle track and the road area, the problems that manual identification is carried out by workers through inquiring monitoring videos, cost is high, detection efficiency is low, and detection omission possibly exists are solved, the abnormal driving behaviors of the road are identified rapidly and accurately, and traffic safety is guaranteed.
It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for detecting abnormal driving according to an embodiment of the present invention;
fig. 2 is a flowchart of an abnormal driving detection method according to a second embodiment of the present invention;
fig. 3 is a flowchart of a method for detecting abnormal driving according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an abnormal driving detection apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing the abnormal driving detection method according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," "target," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of an abnormal driving detection method according to an embodiment of the present invention, which is applicable to identify abnormal driving behaviors on roads, and the method may be implemented by an abnormal driving detection device, which may be implemented in a form of hardware and/or software, and the abnormal driving detection device may be configured in an electronic device with data processing capability. As shown in fig. 1, the method includes:
and S110, acquiring at least two continuous microwave radar images matched with the road area.
The road area may be an area where traffic flow is relatively dense or abnormal driving behaviors such as reversing, illegal lane changing and the like are easy to occur, exemplarily, the road area may be an area such as a high-speed ramp, a junction, a diversion intersection, a high-speed toll gate, an emergency lane and the like, the microwave radar image refers to an image formed by transmitting radio waves to the road area by a radar transmitter and receiving scattered echoes by a receiver. And the gray value of each pixel point in the microwave radar image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area. The microwave radar image corresponds to the road area, each pixel point represents each corresponding sub-area in the road area, and the position, gray value and other information of each pixel point can reflect the information of each sub-area. For example, the vehicle in the road area may cause the radar reflection wave signal intensity at the position to be higher, and the signal intensity of the radar reflection wave is represented in the form of the gray value of the pixel point, so that the microwave radar image may reflect the vehicle information in the road area.
In the embodiment of the application, the abnormal driving behavior is judged through the microwave radar images, so that at least two microwave radar images are needed to determine the driving track of the vehicle and the like. Specifically, at least two microwave radar images of the road area are obtained through the microwave radar and stored for use in the subsequent steps.
And S120, performing background separation on each microwave radar image to obtain a foreground image matched with each microwave radar image.
In this embodiment, the background may be an image of an inherent object in a corresponding road area in the microwave radar image, for example, a road, a sign, and the like of the road area may be the background. The foreground image is an image obtained by separating a background in the microwave radar image.
In the embodiment of the present application, optionally, background separation is performed on each microwave radar image to obtain a foreground image matched with each microwave radar image, including steps A1-A2:
step A1, performing image difference processing on each microwave radar image and a preset average background image to obtain a difference image matched with each microwave radar image.
The average background image is obtained by performing accumulation and averaging according to at least two background images, and the background images are used for representing the signal intensity of radar reflected waves when the microwave radar scans each background area in the road area. The image difference processing may be difference processing of the pixel values of two similar images. For example, the background image may be acquired when the road area is free of traffic.
In this scheme, the setting process of the average background image may be: determining at least two background images; and taking the average value of the gray values of the target pixel points in each background image as the gray value of the target pixel points in the average background image.
Specifically, a microwave radar is used for scanning a road area to obtain at least two background images, each background image can be marked as F', and is provided with P rows and Q columns, namely a gray image formed by P × Q pixel points, and the matrix is expressed as follows:
Figure BDA0003825934990000061
further, the gray value of each pixel point of the average background image is obtained by averaging the gray values of the pixel points corresponding to each background image by f 11 Taking pixel point as example, average f in background image 11 The gray value of the pixel point is determined by f in each background image 11 The gray value of the pixel point is obtained by averaging, and in the process, f 11 Namely the target pixel point. Traversing all target pixel points to obtain an average background image
Figure BDA0003825934990000066
Expressed by the formula:
Figure BDA0003825934990000062
wherein, F i ' is a grayscale map of each of the background images, and N is the number of background images.
In the embodiment of the application, the microwave radar image and the average background image are subjected to image difference processing to obtain a difference image F Δ It can be expressed as:
Figure BDA0003825934990000063
wherein, F is a gray scale image of the microwave radar image.
And step A2, carrying out binarization processing on each difference image, and taking the image after binarization processing as a foreground image.
The binarization processing may be that each pixel in the image has only two possible values or gray scale states, that is, the gray scale value of any pixel in the image is 0 or 255, which respectively represents black and white.
Specifically, the binarization processing may be performed by the following formula:
Figure BDA0003825934990000064
wherein, f ij ' is the gray value of the corresponding pixel point of the radar image after the binarization processing,
Figure BDA0003825934990000065
the gray value of the corresponding pixel point in the difference image is the gray value, T is a preset gray value, the preset gray value may be a critical value of converting the gray value of the corresponding pixel point in the microwave radar image into 0 or 255, when the gray value of the corresponding pixel point in the microwave radar image is greater than or equal to the preset gray value, the gray value of the corresponding pixel point is converted into 255, otherwise, the gray value is converted into 0. The preset gray value can be determined according to actual conditions, and the preset gray value is not limited in the embodiment of the application.
And S130, determining at least one target vehicle track according to each foreground image.
Wherein the target vehicle is used to detect the presence or absence of abnormal driving behavior. The target vehicle trajectory may be a travel trajectory of the target vehicle. Specifically, the target vehicle trajectory may be determined according to the position of the target vehicle in each foreground image. For example, taking the determination of the track of one target vehicle in each foreground image as an example, the positions of the target vehicles at the acquisition time points of each microwave radar image may be determined according to each foreground image, and the track of the target vehicle may be determined according to each position of the target vehicle.
In this embodiment of the present application, optionally, determining at least one target vehicle track according to each foreground image includes: determining at least two target vehicle areas according to each foreground image; and determining the target vehicle track according to each target vehicle area.
In the scheme, the foreground images may include target vehicles and other objects, the areas where the target vehicles are located in the foreground images need to be determined, and then the tracks of the target vehicles are determined according to the areas of the target vehicles, so that interference of the other objects in the foreground images is avoided.
Specifically, the information such as the size and the outline of the target vehicle is different from that of other objects in each foreground image, the target vehicle area is screened out from each foreground image according to the information, at least two position points are obtained when the target vehicle approaches the road area, and the vehicle track is determined according to a vehicle track algorithm. The vehicle trajectory algorithm may estimate the vehicle trajectory according to at least two vehicle regions, and the embodiment does not limit the specific type of the vehicle trajectory algorithm used.
And S140, judging whether abnormal driving behaviors exist or not according to the target vehicle track and the road area.
Specifically, after the target vehicle track is obtained, whether the target vehicle has abnormal driving behaviors or not is adaptively judged according to the target vehicle track and the road characteristics of the road. For example, when the road area is a high-speed exit area, if the target vehicle track is arc-shaped, the target vehicle track conforms to the road curve of the high-speed exit area, and the target vehicle has no abnormal driving behavior; if the target vehicle track contains an obvious steering track, the target vehicle may suddenly change the lane at the high-speed exit position, and abnormal driving behaviors can be judged to exist; and if the target vehicle track stops at a certain position, judging that the target vehicle has abnormal driving behaviors. Obviously, abnormal driving behaviors such as reversing and retrograde motion exist, and the judgment modes are not exemplified.
According to the technical scheme, background separation is carried out on each microwave radar image through at least two continuous microwave radar images matched with the road area to obtain the foreground image matched with each microwave radar image, at least one target vehicle track is determined according to each foreground image, whether abnormal driving behaviors exist or not is judged according to the target vehicle track and the road area, the problems that manual identification is carried out by workers through inquiring monitoring videos, cost is high, detection efficiency is low, and detection omission possibly exists are solved, the abnormal driving behaviors in the road are identified quickly and accurately, and traffic safety is guaranteed.
Example two
Fig. 2 is a flowchart of an abnormal driving detection method according to a second embodiment of the present invention, and this embodiment optimizes determining whether an abnormal driving behavior exists based on the second embodiment.
As shown in fig. 2, the method of the present embodiment is specifically optimized as follows:
and S210, acquiring at least two continuous microwave radar images matched with the road area.
And S220, performing background separation on each microwave radar image to obtain a foreground image matched with each microwave radar image.
And S230, determining at least one target vehicle track according to each foreground image.
And S240, determining a standard vehicle track matched with the road area.
The standard vehicle track refers to a driving track of a vehicle passing through a road area normally. In the embodiment of the present application, optionally, the setting process of the standard vehicle trajectory includes steps B1 to B3:
and B1, acquiring at least two continuous standard images obtained when the test vehicle runs in the road area.
The grey value of each pixel point in the standard image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area when the test vehicle runs in the road area.
In the scheme, the test vehicle is allowed to run in the road area in advance, and the running track is obtained so as to determine the standard vehicle track. Specifically, the test vehicle runs in a road area, at least two continuous microwave radar images of the test vehicle are obtained, if the test vehicle has line pressing and other abnormalities in the process of running, the at least two continuous microwave radar images are obtained again, and the at least two continuous microwave radar images obtained in one-time running with the most reasonable running track are used as standard images.
And B2, performing background separation on each standard image to obtain a standard foreground image matched with each standard image.
Wherein the standard foreground image comprises an image of the test vehicle in the road region. The embodiments of the present application have been described in detail, and are not described herein again.
And B3, determining a standard vehicle track according to each standard foreground image.
The embodiment of the present application has been described in detail, and the determination methods of the standard vehicle trajectories are consistent and will not be described here.
And S250, if the similarity between the target vehicle track and the standard vehicle track is lower than a preset similarity threshold value, determining that abnormal driving behaviors exist.
The similarity is the similarity between the target vehicle track and the standard vehicle track, the higher the coincidence degree of the target vehicle track and the standard vehicle track is, the higher the similarity is, and the lower the coincidence degree of the target vehicle track and the standard vehicle track is, the lower the similarity is. The preset similarity threshold may be determined according to actual conditions, which is not limited in the embodiment of the present application. Specifically, if the similarity between the target vehicle trajectory and the standard vehicle trajectory is lower than the preset similarity threshold, it indicates that the driving trajectory of the target vehicle deviates from the standard vehicle trajectory, and abnormal driving behaviors such as parking, reversing, backing and the like may occur.
According to the technical scheme, background separation is carried out on each microwave radar image through at least two continuous microwave radar images matched with the road area, foreground images matched with each microwave radar image are obtained, at least one target vehicle track is determined according to each foreground image, if the similarity between the target vehicle track and the standard vehicle track is determined to be lower than a preset similarity threshold value, abnormal driving behaviors are determined, the problems that the cost is high, the detection efficiency is low and detection omission possibly exists due to manual identification of workers through inquiring monitoring videos are solved, the abnormal driving behaviors in the road are rapidly and accurately identified, and traffic safety is guaranteed.
In this embodiment of the application, optionally, the acquiring at least two continuous microwave radar images matched with the road area includes: and respectively acquiring at least two continuous microwave radar images for at least one lane in the road area. Further, determining at least one target vehicle trajectory according to each foreground image, comprising: and respectively determining at least one target vehicle track matched with each lane according to the foreground image corresponding to each lane. Further, according to the target vehicle track and the road area, judging whether an abnormal driving behavior exists or not includes: and judging whether abnormal driving behaviors exist or not according to the target lane and at least one target vehicle track matched with the target lane.
Specifically, due to the fact that the abnormal driving behaviors of the vehicles on different lanes are different, the abnormal driving behavior of the target vehicle is adaptively judged according to different lanes. For example, taking a road area as an exit of a highway as an example, there may be a lower expressway and two straight lanes, and if the target vehicle travels in the straight lanes and the target vehicle trajectory deviates at the exit of the highway, the target vehicle may change lanes with a solid line, which is an abnormal driving behavior.
According to the scheme, at least one target vehicle track matched with each lane is determined according to different lanes, and whether abnormal driving behaviors exist or not is judged according to the at least one target vehicle track matched with the target lanes, so that the accuracy of judging the abnormal driving behaviors is improved.
EXAMPLE III
Fig. 3 is a flowchart of an abnormal driving detection method according to a third embodiment of the present invention, which is embodied in the present embodiment based on the foregoing embodiment.
As shown in fig. 3, the method of the present embodiment includes:
s310, at least two continuous microwave radar images matched with the road area are obtained.
S320, determining at least one normal distribution model matched with target pixel points in the target microwave radar image.
The number of the target microwave radar images is at least two, and when background separation is carried out on a certain microwave radar image, the image is the target microwave radar image. Similarly, when a certain pixel point of the target microwave radar image is analyzed, the pixel point is a target pixel point. And the normal distribution model is used for expressing the distribution condition of the signal intensity of radar reflected waves when the microwave radar scans a target background area in a road area matched with the target pixel points.
In the scheme, under the condition that other parameters are not changed, when the microwave radar conducts multiple times of detection on a certain fixed area, the signal intensity of a plurality of radar reflected waves is in normal distribution, and therefore all detection areas of a road area are matched with at least one normal distribution model.
S330, judging whether the target pixel points accord with normal distribution or not according to the gray value of the target pixel points and the normal distribution models.
Specifically, after the microwave radar image is obtained, whether the gray value of a target pixel point in the target microwave radar image is matched with the matched normal distribution model or not is judged, if the gray value of the target pixel point is matched with any one of the matched normal distribution models, the target pixel point accords with the normal distribution, and if not, the target pixel point does not accord with the normal distribution.
In this embodiment of the application, optionally, according to the gray value of the target pixel and each normal distribution model, determine whether the target pixel accords with normal distribution, including: and if the mean value of at least one normal distribution model and the gray value of the target pixel point meet the Lauder criterion, determining that the target pixel point accords with normal distribution.
The Laviand criterion can be expressed by the following formula:
Figure BDA0003825934990000111
in the formula, x ij Is the gray value of the target pixel point,
Figure BDA0003825934990000112
is the mean value in the normal distribution model corresponding to the target pixel point,
Figure BDA0003825934990000113
is the variance in the normal distribution model corresponding to the target pixel point.
Specifically, if the gray value of the target pixel meets the above-mentioned Lauder criterion, the target pixel is in accordance with normal distribution. Furthermore, all pixel points in the target microwave radar image can be traversed, and whether each pixel point accords with normal distribution or not is determined.
And S340, obtaining a foreground image matched with the target microwave radar image according to the pixel points which do not accord with the normal distribution in the target microwave radar image.
In the embodiment of the application, if a certain pixel point is not in accordance with normal distribution, vehicles may exist in a detection area corresponding to the pixel point, so that the intensity of a received radar reflected wave signal changes, and therefore, each pixel point which is not in accordance with normal distribution in a target microwave radar image is separated from other pixel points, and a separated foreground image is obtained.
And S350, determining at least one target vehicle track according to each foreground image.
And S360, judging whether abnormal driving behaviors exist or not according to the target vehicle track and the road area.
According to the technical scheme of the embodiment of the application, at least one normal distribution model matched with target pixel points in a target microwave radar image is determined through at least two continuous microwave radar images matched with a road area; judging whether the target pixel points accord with normal distribution or not according to the gray value of the target pixel points and each normal distribution model; obtaining a foreground image matched with the target microwave radar image according to each pixel point which does not accord with normal distribution in the target microwave radar image; and determining at least one target vehicle track according to each foreground image, and if the similarity between the target vehicle track and the standard vehicle track is determined to be lower than a preset similarity threshold, determining that abnormal driving behaviors exist, so that the problems of high cost, low detection efficiency and possible omission caused by manual identification of workers through inquiring monitoring videos are solved, the abnormal driving behaviors in the road are quickly and accurately identified, and traffic safety is guaranteed.
In the embodiment of the present application, optionally, the setting process of the at least one normal distribution model matched with the target pixel points in the target microwave radar image includes the following steps C1 to C3:
and step C1, determining the mean value and the variance of the gray values according to the gray values of the target pixel points in the background images with the first preset number.
The first preset number may be determined according to an actual situation, and is not limited in the embodiment of the present application. In the embodiment of the application, the normal distribution model should reflect the gray value distribution of the pixel points in the corresponding detection area in the state of no foreign matter as much as possible, a first preset number of background images can be obtained after no vehicle exists in the road area, and the mean value and the variance of the gray values are obtained for the target pixel points of the background images.
Step C2, determining an initial normal distribution model according to the gray value mean value and the gray value variance; the weight of the initial normal distribution model is an initial weight.
The initial weight may be determined according to an actual situation, which is not limited in this embodiment of the present application. In this embodiment of the application, a target pixel point may correspond to multiple normal distribution models, and the weight of each normal distribution model may be different, for example, a certain target pixel point corresponds to an a normal distribution model and a B normal distribution model, and the probability that the target pixel point conforms to the a normal distribution model is higher, and the weight of the a normal distribution model should be higher. In this step, according to the gray value mean and the gray value variance obtained in step C1, the initial normal distribution model and the initial weight are determined first, so that the initial normal distribution model and the initial weight are adaptively adjusted in the subsequent steps.
And C3, adjusting the initial normal distribution model or adding a new normal distribution model according to the gray values of the target pixel points in the background images with the second preset number.
The second preset number may be determined according to an actual situation, and is not limited in the embodiment of the present application. Illustratively, whether the gray values of the target pixel points in the second preset number of background images accord with the initial normal distribution model or not is sequentially judged, if so, the weight of the initial normal distribution model can be increased, and the initial normal distribution model is adaptively adjusted according to the gray values of the target pixel points. If the initial normal distribution model is not met, the weight of the initial normal distribution model can be reduced, and meanwhile, a normal distribution model is added.
Obviously, after the normal distribution model is newly added, when whether the gray value of the target pixel point in the background image conforms to the normal distribution model is continuously judged, a plurality of corresponding normal distribution models may exist, which normal distribution model belongs to can be sequentially judged from large to small according to the weight of each normal distribution model, and the weight of the normal distribution model is adjusted, or the normal distribution model is newly added.
In the scheme, the mean value and the variance of the gray values are determined according to the gray values of target pixel points in a first preset number of background images; and then determining the weight and the initial weight of the initial normal distribution model, adjusting the initial normal distribution model according to the gray values of target pixel points in a second preset number of background images, or adding a new normal distribution model, ensuring the accuracy of the normal distribution model, and improving the completeness of the target pixel points corresponding to the normal distribution model.
In this embodiment, optionally, the adjusting of the initial normal distribution model or the adding of the new normal distribution model according to the gray values of the target pixel points in the second preset number of background images includes the following steps D1 to D3:
and D1, if the mean value of the initial normal distribution model is determined and meets the Lareach criterion with the gray value of the target pixel point in the target background image, adjusting the mean value and the variance of the initial normal distribution model according to a preset learning rate, and improving the weight of the initial normal distribution model.
And judging the relationship between the target pixel point gray value of each background image and the normal distribution model in the second preset number of background images, wherein the current background image needing to be judged is the target background image. The preset learning rate may be used to represent an adjustment range for adjusting the mean, the variance, and the weight of the normal distribution model corresponding to the target detection area. The specific value of the preset learning rate can be determined according to actual conditions, and the embodiment of the application does not limit the specific value.
Specifically, the gray value of the target pixel point in the target background image and the mean value and the variance of the initial normal distribution model are brought into a specific formula of the Lauder criterion, and if the Lauder criterion is met, the mean value of the target pixel point corresponding to the initial normal distribution model is subjected to learning according to a preset learning rate
Figure BDA0003825934990000141
Variance (variance)
Figure BDA0003825934990000142
And weight
Figure BDA0003825934990000143
Adjusting to obtain an adjusted average value
Figure BDA0003825934990000144
Variance (variance)
Figure BDA0003825934990000145
And weight
Figure BDA0003825934990000146
The adjustment formula may be:
Figure BDA0003825934990000147
Figure BDA0003825934990000148
Figure BDA0003825934990000149
in the formula, alpha is a preset learning rate, x ij,t And the gray value of the target pixel point in the target background image is obtained. The specific formula of the Layouda criterion is given, and the scheme is not repeated.
And D2, if the mean value of the initial normal distribution model is determined and the gray value of the target pixel point in the target background image does not meet the Lauda criterion, reducing the weight of the initial normal distribution model.
Specifically, the gray value of the target pixel point in the target background image and the mean and the variance of the initial normal distribution model are brought into a specific formula of the Lauda criterion, if the Lauda criterion is not satisfied, the gray value of the target pixel point is not adapted to the initial normal distribution model, the weight of the initial normal distribution model can be reduced, and the formula for reducing the weight is as follows:
Figure BDA0003825934990000151
further, if the weight of an initial normal distribution model is reduced below the weight threshold, which indicates that the initial normal distribution model may have problems, the initial normal distribution model may be deleted. The weight threshold may be determined according to an actual situation, which is not limited in the embodiment of the present application.
Step D3, if the gray value of the target pixel point in the target background image is determined, and all normal distribution models matched with the target detection area do not meet the Lauda criterion, generating a new normal distribution model according to the gray value of the target pixel point in the target background image and the gray value variance of the target pixel point in the target background image; and the weight of the newly added normal distribution model is a preset learning rate.
Specifically, if the gray value of the target pixel point in the target background image does not satisfy the rale criterion in each normal distribution model matched with the target detection area, the gray value of the target pixel point may belong to a new normal distribution model, a new normal distribution model may be established according to the gray value of the target pixel point in the target background image and the gray value variance of the target pixel point in the target background image, and subsequently, steps D1 to D3 may be repeatedly performed on the remaining background images to perfect the new normal distribution model and the corresponding weights.
In the scheme, the initial normal distribution model is adjusted or a new normal distribution model is added according to the gray values of the target pixel points in the second preset number of background images to obtain a plurality of normal distribution models and weights corresponding to the normal distribution models, and the weights are normalized to facilitate the use of the normal distribution models. Specifically, the formula of the normalization process is as follows:
Figure BDA0003825934990000161
where K is the number of weights.
Example four
Fig. 4 is a schematic structural diagram of an abnormal driving detection apparatus provided in a fourth embodiment of the present invention, which is capable of executing the abnormal driving detection method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method. As shown in fig. 4, the apparatus includes:
the image acquisition module 410 is used for acquiring at least two continuous microwave radar images matched with a road area;
the gray value of each pixel point in the microwave radar image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area;
the background separation module 420 is configured to perform background separation on each microwave radar image to obtain a foreground image matched with each microwave radar image;
a vehicle track determining module 430, configured to determine at least one target vehicle track according to each foreground image;
and the driving behavior judging module 440 is configured to judge whether an abnormal driving behavior exists according to the target vehicle trajectory and the road area.
Optionally, the background separation module 420 includes:
the difference processing unit is used for carrying out image difference processing on each microwave radar image and a preset average background image to obtain a difference image matched with each microwave radar image;
the average background image is obtained by accumulating and averaging at least two background images, and the background images are used for representing the signal intensity of radar reflected waves when the microwave radar scans each background area in the road area;
and the binarization processing unit is used for carrying out binarization processing on each difference image and taking the image after the binarization processing as a foreground image.
Optionally, the background separation module 420 includes:
the normal distribution model determining unit is used for determining at least one normal distribution model matched with target pixel points in the target microwave radar image;
the normal distribution model is used for expressing the distribution condition of the signal intensity of radar reflected waves when the microwave radar scans a target background area in a road area matched with the target pixel points;
the pixel point judging unit is used for judging whether the target pixel points accord with normal distribution or not according to the gray value of the target pixel points and each normal distribution model;
and the foreground image determining unit is used for obtaining a foreground image matched with the target microwave radar image according to the pixel points which are not in accordance with the normal distribution in the target microwave radar image.
Optionally, the vehicle track determining module 430 includes:
the target vehicle area determining unit is used for determining at least two target vehicle areas according to each foreground image;
and the target vehicle track determining unit is used for determining the target vehicle track according to each target vehicle area.
Optionally, the driving behavior determination module 440 includes:
a standard vehicle track determination unit for determining a standard vehicle track matching the road area;
and the abnormal driving behavior judging unit is used for determining that abnormal driving behaviors exist if the similarity between the target vehicle track and the standard vehicle track is lower than a preset similarity threshold value.
Optionally, the standard vehicle trajectory setting process includes:
acquiring at least two continuous standard images obtained when a test vehicle runs in a road area;
the gray value of each pixel point in the standard image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area when the test vehicle runs in the road area;
carrying out background separation on each standard image to obtain a standard foreground image matched with each standard image;
and determining a standard vehicle track according to each standard foreground image.
Optionally, the image obtaining module 410 includes:
the microwave radar image acquisition unit is used for respectively acquiring at least two continuous microwave radar images for at least one lane in a lane area;
optionally, the vehicle track determining module 430 includes:
the target vehicle track determining unit is used for respectively determining at least one target vehicle track matched with each lane according to the foreground image corresponding to each lane;
optionally, the driving behavior determination module 440 includes:
and the abnormal driving behavior judging unit is used for judging whether abnormal driving behaviors exist or not according to the target lane and at least one target vehicle track matched with the target lane.
The abnormal driving detection device provided by the embodiment of the invention can execute the abnormal driving detection method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
FIG. 5 illustrates a block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as the abnormal driving detection method.
In some embodiments, the abnormal driving detection method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the abnormal driving detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the abnormal traffic detection method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An abnormal driving detection method is characterized by comprising the following steps:
acquiring at least two continuous microwave radar images matched with a road area;
the gray value of each pixel point in the microwave radar image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area;
background separation is carried out on each microwave radar image to obtain a foreground image matched with each microwave radar image;
determining at least one target vehicle track according to each foreground image;
and judging whether abnormal driving behaviors exist or not according to the target vehicle track and the road area.
2. The method of claim 1, wherein background separating each microwave radar image to obtain a foreground image matched with each microwave radar image comprises:
carrying out image difference processing on each microwave radar image and a preset average background image to obtain a difference image matched with each microwave radar image;
the average background image is obtained by accumulating and averaging at least two background images, and the background images are used for representing the signal intensity of radar reflected waves when the microwave radar scans each background area in the road area;
and carrying out binarization processing on each difference image, and taking the image after binarization processing as a foreground image.
3. The method of claim 1, wherein background separating each microwave radar image to obtain a foreground image matched with each microwave radar image comprises:
determining at least one normal distribution model matched with target pixel points in a target microwave radar image;
the normal distribution model is used for representing the distribution condition of the signal intensity of radar reflected waves when the microwave radar scans a target background area in a road area matched with the target pixel points;
judging whether the target pixel points accord with normal distribution or not according to the gray value of the target pixel points and each normal distribution model;
and obtaining a foreground image matched with the target microwave radar image according to the pixel points which do not accord with the normal distribution in the target microwave radar image.
4. The method of claim 1, wherein determining at least one target vehicle trajectory from each foreground image comprises:
determining at least two target vehicle areas according to each foreground image;
and determining a target vehicle track according to each target vehicle area.
5. The method of claim 1, wherein determining whether abnormal driving behavior exists according to the target vehicle trajectory and the road area comprises:
determining a standard vehicle track matched with the road area;
and if the similarity between the target vehicle track and the standard vehicle track is lower than a preset similarity threshold, determining that abnormal driving behaviors exist.
6. The method of claim 5, wherein the standard vehicle trajectory is set by:
acquiring at least two continuous standard images obtained when a test vehicle runs in a road area;
the gray value of each pixel point in the standard image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area when the test vehicle runs in the road area;
carrying out background separation on each standard image to obtain a standard foreground image matched with each standard image;
and determining a standard vehicle track according to each standard foreground image.
7. The method of claim 1, wherein acquiring at least two consecutive microwave radar images matching a road region comprises:
respectively acquiring at least two continuous microwave radar images for at least one lane in a road area;
determining at least one target vehicle trajectory from each foreground image, comprising:
respectively determining at least one target vehicle track matched with each lane according to the foreground image corresponding to each lane;
judging whether abnormal driving behaviors exist or not according to the target vehicle track and the road area, wherein the judging step comprises the following steps:
and judging whether abnormal driving behaviors exist or not according to the target lane and at least one target vehicle track matched with the target lane.
8. An abnormal-traveling detection device, characterized by comprising:
the image acquisition module is used for acquiring at least two continuous microwave radar images matched with the road area;
the gray value of each pixel point in the microwave radar image is used for representing the signal intensity of radar reflected waves when the microwave radar scans each detection area in the road area;
the background separation module is used for carrying out background separation on each microwave radar image to obtain a foreground image matched with each microwave radar image;
the vehicle track determining module is used for determining at least one target vehicle track according to each foreground image;
and the driving behavior judging module is used for judging whether abnormal driving behaviors exist according to the target vehicle track and the road area.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the abnormal driving detection method of any one of claims 1 to 7.
10. A computer-readable storage medium storing computer instructions for causing a processor to implement the abnormal driving detection method according to any one of claims 1 to 7 when executed.
CN202211059053.1A 2022-08-31 2022-08-31 Abnormal driving detection method and device, electronic equipment and medium Pending CN115526837A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211059053.1A CN115526837A (en) 2022-08-31 2022-08-31 Abnormal driving detection method and device, electronic equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211059053.1A CN115526837A (en) 2022-08-31 2022-08-31 Abnormal driving detection method and device, electronic equipment and medium

Publications (1)

Publication Number Publication Date
CN115526837A true CN115526837A (en) 2022-12-27

Family

ID=84696822

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211059053.1A Pending CN115526837A (en) 2022-08-31 2022-08-31 Abnormal driving detection method and device, electronic equipment and medium

Country Status (1)

Country Link
CN (1) CN115526837A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116758081A (en) * 2023-08-18 2023-09-15 安徽乾劲企业管理有限公司 Unmanned aerial vehicle road and bridge inspection image processing method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116758081A (en) * 2023-08-18 2023-09-15 安徽乾劲企业管理有限公司 Unmanned aerial vehicle road and bridge inspection image processing method
CN116758081B (en) * 2023-08-18 2023-11-17 安徽乾劲企业管理有限公司 Unmanned aerial vehicle road and bridge inspection image processing method

Similar Documents

Publication Publication Date Title
CN112818792A (en) Lane line detection method, lane line detection device, electronic device, and computer storage medium
CN112863187B (en) Detection method of perception model, electronic equipment, road side equipment and cloud control platform
CN113538963A (en) Method, apparatus, device and storage medium for outputting information
CN113989777A (en) Method, device and equipment for identifying speed limit sign and lane position of high-precision map
CN115359471A (en) Image processing and joint detection model training method, device, equipment and storage medium
CN115526837A (en) Abnormal driving detection method and device, electronic equipment and medium
CN115376106A (en) Vehicle type identification method, device, equipment and medium based on radar map
CN115761698A (en) Target detection method, device, equipment and storage medium
CN115436900A (en) Target detection method, device, equipment and medium based on radar map
CN113139488B (en) Method and device for training segmented neural network
CN115330841A (en) Method, apparatus, device and medium for detecting projectile based on radar map
CN113011316B (en) Method and device for detecting lens state, electronic equipment and medium
CN113989300A (en) Lane line segmentation method and device, electronic equipment and storage medium
CN115424442A (en) Radar map-based vehicle driving event detection method, device, equipment and medium
CN115375666A (en) Traffic accident detection method and device, electronic equipment and storage medium
CN115424441B (en) Road curve optimization method, device, equipment and medium based on microwave radar
CN115410370A (en) Abnormal parking detection method and device, electronic equipment and storage medium
CN114581890B (en) Method and device for determining lane line, electronic equipment and storage medium
CN114067565B (en) Method and device for determining congestion identification accuracy
CN112784789B (en) Method, device, electronic equipment and medium for identifying traffic flow of road
CN115359087A (en) Radar image background removing method, device, equipment and medium based on target detection
CN114565889B (en) Method and device for determining vehicle line pressing state, electronic equipment and medium
CN115267782A (en) Dangerous area early warning method, device, equipment and medium based on microwave radar
CN114898323A (en) Scene matching method and device, electronic equipment and storage medium
CN114842465A (en) License plate detection method and device, electronic equipment, medium and intelligent transportation equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination